• Journal of the Korean Society of School Health
• /
• v.36 no.3
• /
• pp.113-125
• /
• 2023

Purpose: The purpose of this study is to develop a model for predicting mental health risk among adolescents based on health behavior information by employing a hybrid machine learning method. Methods: The study analyzed data of 51,850 domestic middle and high school students from 2022 Youth Health Behavior Survey conducted by the Korea Disease Control and Prevention Agency. Firstly, mental health risk levels (stress perception, suicidal thoughts, suicide attempts, suicide plans, experiences of sadness and despair, loneliness, and generalized anxiety disorder) were classified using the k-mean unsupervised learning technique. Secondly, demographic factors (family economic status, gender, age), academic performance, physical health (body mass index, moderate-intensity exercise, subjective health perception, oral health perception), daily life habits (sleep time, wake-up time, smartphone use time, difficulty recovering from fatigue), eating habits (consumption of high-caffeine drinks, sweet drinks, late-night snacks), violence victimization, and deviance (drinking, smoking experience) data were input to develop a random forest model predicting mental health risk, using logistic and XGBoosting. The model and its prediction performance were compared. Results: First, the subjects were classified into two mental health groups using k-mean unsupervised learning, with the high mental health risk group constituting 26.45% of the total sample (13,712 adolescents). This mental health risk group included most of the adolescents who had made suicide plans (95.1%) or attempted suicide (96.7%). Second, the predictive performance of the random forest model for classifying mental health risk groups significantly outperformed that of the reference model (AUC=.94). Predictors of high importance were 'difficulty recovering from daytime fatigue' and 'subjective health perception'. Conclusion: Based on an understanding of adolescent health behavior information, it is possible to predict the mental health risk levels of adolescents and make interventions in advance.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.761-772
• /
• 2021

This study aims to investigate the effect of violence experience and self-esteem experienced in social scenes such as work and school on suicidal thoughts. For this purpose, I used the Ministry of Gender Equality and Family(2017)'s data of the current situation of social violence victims. To this end, descriptive statistics, correlation, and hierarchical binary logistic regression analysis were performed. The findings of this study are as follows: The experience of social violence among North Korean refugee women had a positive effect on suicidal thoughts, and self-esteem had a negative effect on suicide-related features. This means that if you have experienced social violence, you are more likely to have suicidal thinking, and the higher your self-esteem is, the less likely your suicidal thinking is. Based upon the results of this study, practical intervention measures were proposed to prevent social violence, and to improve physical/mental health and self-esteem of North Korean refugee women.

• Korean Journal of Psychosomatic Medicine
• /
• v.28 no.1
• /
• pp.8-19
• /
• 2020

Objectives : The purpose of this study was to examine whether the MMPI-2-RF serves as a useful tool to differentiate between the subtypes of high risk of suicide among psychiatric outpatients. Methods : Patients were recruited from the department of psychiatry of university hospital. Participants were diagnosed using DSM-5 criteria by board certified psychiatrists. Their medical records were reviewed retrospectively. And participants were put into 4 groups (Suicide ideation, Suicide attempt, Non-suicidal self-injury, and general psychiatric diagnosis as a control group). For statistical comparison, the MANCOVA with gender as a covariate was used. Results : The results indicated that as previous research with non-clinical sample suggested, psychiatric outpatients with high suicide risk also have significantly higher Emotional/Internalizing Dysfunction, Helplessness/Hopelessness, Suicidal/Death Ideation, Demoralization, Cognitive complaints, Cynicism, Dysfunctional negative thoughts than general psychiatric patients group. But group differences within the high suicide risk patients have not been observed. However, suicide attempt group and NSSI group has higher Behavioral/Externalizing Dysfunction, RC4, AGG than general psychiatric patients group. But there was no difference between suicidal idea group and general psychiatric patients group. Conclusions : There was no group difference observed between all three subtypes, which mean the MMPI2-RF may not be the useful diagnostic tool to navigate high suicide risk subtypes. Even though there was no difference observed in the suicide ideation group, suicide attempt group and NSSI group have higher aggression and externalization. So those indexes could serve as a useful marker to investigate riskiness of suicide related symptoms.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.17 no.2
• /
• pp.98-105
• /
• 2006

Objectives : To consider which questions are most useful clinically and to find a framework for assessment of suicidality or risk of suicide for adolescents. Methods : Authors reviewed and integrated both clinical works and researches about measures used to evaluate suicidal behaviors in adolescents. Results : The 'cascade approach' for assessment of suicidality was developed; the quality and quantity of 'distress' leads to an entry question to do with the 'quality of life' and whether it is worth living. These two questions lead to examinations of 'thoughts' which may lead to 'plans' which leads to 'threats' which then leads to 'deliberate self injury' and then on to a history of 'past suicide attempts'. Authors also suggested to use a summed score of cascade approach in clinical decisions and showed how to modify it up to different evaluation situations. Focusing on the good things helps not only to qualify suicidality but also to begin the search for solutions. Conclusion : In the clinical assessment process, while scales assist the clinician, there is nothing to supplant a sensitive clinical approach. The 'cascade approach' was proposed as a framework for assessing adolescents for suicidality.

• Journal of Korean Academy of Nursing
• /
• v.39 no.4
• /
• pp.459-468
• /
• 2009

Purpose: The purpose of the study was to investigate psychological factors such as eating psychopathology, depression, and obsessive-compulsion that might influence self-harm behavior in patients with eating disorders. Methods: Patients with eating disorders (n=135) who visited "M" clinic for eating disorders participated in the study. Data were collected from March to August 2007 using the Eating Disorder Inventory-2, Beck Depression Inventory, Maudsley Obsessional-Compulsive Inventory, and Self-Harm Inventory (SHI). Results: The participants scored high on self-harm as well as on depression and obsessive-compulsion. On the SHI, a high frequency of self harm behavior such as 'torturing self with self-defeating thoughts', 'abused alcohol', 'hit self', and 'suicide attempt' were found for the participants. There were significant correlations between most eating psychopathology variables, depression, obsessive-compulsion, and self-harm behavior. 'Interoceptive awareness' (eating psychopathology), depression, and 'checking' (obsessive-compulsion) were significant predictors of self-harm behavior. Conclusion: Future interventions for patients with eating disorders should focus on assessing the possibility of self-harm and suicidal attempts, especially in those patients with high levels of eating psychopathology, depression, or obsessive-compulsion. Early intervention for depression and obsessive-compulsion could contribute to preventing self-harm and suicide in patients with eating disorders.

• Journal of the Korean Society of School Health
• /
• v.20 no.1
• /
• pp.11-24
• /
• 2007

Purpose : Health Risk behaviors are a leading cause of preventable morbidity and mortality. Adolescents is a critical transitional period for establishing health behavior for healthy life. The purpose of this study was to describe the types and frequency of the health risk behaviors being performed by middle school students, examine the gender and grade differences of health risk behaviors, and identify the relationship among health risk behaviors. Methods : A total of 1952 early adolescents recruited from 7 middle schools in a district of urban setting completed questionnaires. Youth Risk Behavior Survey-Middle school questionnaires was used to identify the types of health risk behaviors among early adolescents. Data were analyzed by descriptive statistics and Chi-Square test using SAS program . Results : The results showed the frequency for most health risk behaviors and increased with advancing grade level. Males were more likely than females to behaviors related to smoking and violence, whereas females were more likely than males to have suicidal thoughts, be physical inactive and attempt to lose weight. Among health risk behaviors, the relationship of alcohol experience, smoking, and suicide was high. Conclusion : The findings identify a high risk target group among middle school adolescents and suggest that preventive intervention strategies should take into consideration the types with gender and grade, and provided the evidence that one of health risk behaviors may induce the other health risk behaviors.

• Korean Journal of Psychosomatic Medicine
• /
• v.18 no.1
• /
• pp.40-47
• /
• 2010

Objectives：Body image is closely related to self-esteem and weight-control related behaviors. In particular, relationship between two factors would be stronger in female adolescents. False recognition on body image and weight can be a risk factor of eating disorder, depression, and suicidal ideation. This study aimed to examine the effects of body image and eating disorders on developing depressive symptoms and suicidal ideation in female adolescents. Methods：Two hundred thirty nine students of a Girls' Commercial High School in Seoul were recruited. Eating Attitude Test for Korean Adolescents, Self-Esteem Scales, Impulsiveness Scale, Beck's Depression Inventory and Beck's Suicidal Ideation Scale were used to measure eating attitude and severity of psychiatric symptoms. Results：Among 239 subjects, the estimated risk group of eating disorders was 10%(n=24). They experienced more depressive symptoms than the control group. The bigger discrepancy in current and ideal body mass index was significantly related with higher depressive mood, suicidal idea, abnormal eating habits and lower self-esteem. Discrepancy between current and idea BMI was the most meaningful predictive factor about depression and suicidal thoughts by linear regression analysis. Conclusion：In spite of normal weight range of enrolled subjects, they experienced significant depressive mood, suicide thoughts and lower self-esteem associated with the discrepancy of their own subjective body image and current body mass index. Hence educational approach regarding normal body image and healthy weight control is needed for their mental health and preventing eating disorder.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2023

This study developed models using decision forest, support vector machine, and logistic regression methods to predict and prevent suicidal ideation among Korean adolescents. The study sample consisted of 51,407 individuals after removing missing data from the raw data of the 18th (2022) Youth Health Behavior Survey conducted by the Korea Centers for Disease Control and Prevention. Analysis was performed using the MS Azure program with Two-Class Decision Forest, Two-Class Support Vector Machine, and Two-Class Logistic Regression. The results of the study showed that the decision forest model achieved an accuracy of 84.8% and an F1-score of 36.7%. The support vector machine model achieved an accuracy of 86.3% and an F1-score of 24.5%. The logistic regression model achieved an accuracy of 87.2% and an F1-score of 40.1%. Applying the logistic regression model with SMOTE to address data imbalance resulted in an accuracy of 81.7% and an F1-score of 57.7%. Although the accuracy slightly decreased, the recall, precision, and F1-score improved, demonstrating excellent performance. These findings have significant implications for the development of prediction models for suicidal ideation among Korean adolescents and can contribute to the prevention and improvement of youth suicide.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.5
• /
• pp.193-205
• /
• 2020

The purpose of this study was to look into how social support for high school students was affecting suicidal ideation and verify how the moderating effect worked on risk factors in the relationship between social support and suicidal ideation. Specifically, three sub-factors of social support were classified into friend support, teacher support, and parent support, and were set as independent variables. In addition, suicidal ideation was dependent variables, gender, grade level, and school type as moderating variables. The main research results are as follows. First, teacher support, friend support, and parent support all appeared to have a significant negative effect on suicidal ideation. Second, the suicidal thoughts were higher in female students than in male students than in male students and in students of general high school than in those of vocational high school. Third, support from friends and parents was more effects in reducing suicidal thoughts for female students than male students. Fourth, the effect that teacher support that support and parent support reduce suicidal thoughts was greater for first graders than second graders. Bases on the results of the analysis, interviews were also conducted with high school teachers. Through the results of this study, I would like to propose practical measures to alleviate social problems related to suicide in high school students and to provide basic data for policy measures.

• Journal of The Korean Society of Integrative Medicine
• /
• v.8 no.4
• /
• pp.67-77
• /
• 2020

Purpose : Recently, Korea has entered an aging society due to the steadily increasing proportion of the elderly population. Additionally, elderly suicidal rate in Korea is the highest among OECD member countries. Because old age is a time when all functions are weakened physically, mentally, and socially, negative experiences, including depression and poor quality of life in the elderly, may lead to suicidal intentions. This study attempts to understand the relationship between depression and quality of life experienced by the elderly and their suicidal intentions. Methods : The survey was conducted from January 2 to March 31, 2019 by administering a questionnaire targeting people aged ≥ 65 years, who were registered at public health centers located in U-city, Gyeonggi-do. In total, 1,015 copies of data were used for the final analysis. The collected data were analyzed using the SPSS/WIN 23.0 program. The χ2 test was performed to investigate the relationship between the demographic characteristics and the suicidal intentions of the elderly subjects. The t-test was performed to determine the relationship between suicidal intentions, depression, and quality of life in elderly subjects. Results : The study results revealed that 168 people (16.6 %) had thought of suicide and 3.2 % had actually tried to commit suicide. The reasons for suicidal thoughts were family problems in 60 (5.6 %), economic problems in 49 (4.6 %), and physical illness in 44 (4.1 %). Those with suicidal intentions had higher levels of depression (t=11.712, p<.001) and higher quality of life scores (t=-9.565, p<.001). Conclusion : Based on these results, it is proposed that a suicide prevention policy and program that can improve the elderly's depression and quality of life is necessary.